Table 1.

Summary of results highlighting the impact of right-truncation (denoted by T = 6, 3 and 1) on the calculations of statistical power over a range of settings where statistical power was initially between 80% and 85% when no truncation was present (T= ∞) for a single cohort recruited over the trial period. The pre-specified between-cluster variance, ${\sigma }_c^{\mathrm{ }2},$ is the value of the between-cluster variance inputted for simulation of the trial data, and the average empirical between-cluster variance is the mean between-cluster variance estimated from the simulated datasets for each combination of λ and ${\sigma }_c^{\mathrm{ }2}$. The average empirical ICC is the mean intracluster correlation computed as described by Stryhn et al.²⁶ from the simulated datasets

						Statistical power (%)
	Number of clusters	Cluster sizes	Pre-specified between-cluster variance (${\sigma }_{\mathit{c}}^{\mathbf{}2}$)	Average empirical between-cluster variance	Average empirical ICC	T = ∞	T = 6	T = 3	T = 1
Annual event rate (λ) = 1.25	30	15	0.050	0.043	0.038	83.4	80.6	73.4	43.3
	30	45	0.100	0.091	0.078	80.0	77.7	75.7	64.2
	60	35	0.200	0.191	0.150	82.7	82.9	82.2	69.4
	90	40	0.300	0.292	0.210	83.5	85.2	83.4	76.6
	110	40	0.400	0.389	0.260	82.6	80.2	79.8	75.8
Annual event rate(λ) = 2.7	25	10	0.050	0.041	0.074	82.5	79.8	56.9	24.8
	30	30	0.100	0.092	0.153	82.4	79.6	73.2	49.6
	55	20	0.200	0.189	0.269	82.7	78.4	74.4	53.7
	80	30	0.300	0.294	0.360	82.6	79.7	76.8	64.6
	110	25	0.400	0.392	0.427	82.9	82.0	79.8	66.4